calligraphy_lookup_b2b_invoice

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations at all, the description carries the full disclosure burden and falls short: it never says whether this creates persistent artifacts, emails a document (the customer_email default hints at delivery but is never explained), costs money, or is idempotent when called repeatedly for the same job. It also doesn't disclose whether generating an invoice for a job has side effects or whether the certificate is returned inline versus stored.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence that states the lookup, the two generated documents, and the customization fields with no filler. It is efficient, though the compound read+generate framing in one clause makes the two behaviors harder to parse than separate statements would.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a four-parameter tool with no annotations and no output schema, the definition omits too much: the format of the returned invoice/certificate, whether it is emailed to customer_email, prerequisites on job state, and whether repeated calls duplicate documents. An agent would have to guess at nearly all call-time behavior beyond the required job_id.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 25% — job_id is described in the schema, but po_number, company_name, and customer_email are bare. The description clarifies that PO number and company name are printed on the generated documents, which adds meaning for two parameters, but customer_email (with its unusual agent@customer.io default) is never mentioned and its role — billing contact, delivery address, or both — is left entirely ambiguous.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific resource (a Calligraphy EDA job) and two concrete outputs (B2B Tax Invoice and Chain-of-Custody Certificate), with customizable PO number and company name. However, it bundles a read operation ('look up a job') with a generation operation without stating how that relates to the sibling calligraphy_get_job_status, so the boundary is slightly blurred.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance: nothing says whether this should be called after calligraphy_preflight_audit or payment verification, whether the job must be completed first, or when to prefer it over calligraphy_get_job_status for a plain status check. The only usage hint is the job_id schema note pointing back to calligraphy_compile_board.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.